Implementation of Text Mining to Detect Emotions of Fuel Price Increase Using BERT-LSTM Method

Year 2024, Volume: 37 Issue: 4 , 1707 - 1716 , 01.12.2024

Pungkas Subarkah , Hasri Akbar Awal Rozaq , Primandani Arsi , Siti Alvi Sholikhatin , Riyanto Riyanto , Hendra Marcos

https://doi.org/10.35378/gujs.1424742

https://izlik.org/JA36XD65UL

Abstract

Fuel is crucial for everyday life, especially as a primary source of transportation fueled by oil. In early April 2022, Indonesia experienced a significant event that deeply affected its populace: a surge in fuel prices. Addressing this pressing issue, this study employs emotion classification utilizing BERT and LSTM methods on social media data, particularly from platforms like YouTube, to categorize emotional responses to governmental decisions. This research aims to classify social media discourse surrounding fuel-related topics, notably the increases in fuel prices. The highest accuracy, at 95%, was achieved with oversampling techniques, contrasting with a mere 47% accuracy without oversampling. Surprisingly, experiments indicate that employing oversampling and BERT for emotion classification results in reduced accuracy during testing phases.

Keywords

BERT , Emotion , Fuel Price , LSTM , Oil

References

• [1] Danirmala, T., Nugroho, Y. S., “Analisis Sentimen Terhadap Topik Kenaikan Harga Bahan Bakar Minyak (BBM) pada Media Sosial Twitter”, Indonesia Journal of Computer Science, 12(3), (2023).
• [2] Wardani, W., Suriana, S., Arfah, S. U., Zulaili, Z., Lubis, P. S., “Dampak kenaikan Bahan Bakar Minyak (BBM) Terhadap Inflasi dan Implikasinya Terhadap Makroekonomi di Indonesia”, All Fields of Science Journal Liaison Academia and Sosiety, 2: 63–70, (2022).
• [3] Avvisa, A., Nuswardani, N., Darsono, D., “Tinjauan Yuridis Tentang Tanggung Jawab Hukum Terhadap Sewa Menyewa Tangki Minyak Antara PT Karyamas Niaga Manunggal Jaya Dengan Pertamina”, Bachelor Thesis, Muhammadiyah Surakarta University, Surakarta, (2014).
• [4] Silbaqolbina, Y. Z., Najicha, F. U., “Kebijakan Pemerintah Dalam Menaikkan Harga Bahan Bakar Minyak Serta Dampaknya Bagi Masyarakat”, Jurnal Syntax Fusion, 2: 604–611, (2022).
• [5] Sarbaini, S., Nazaruddin, N., “Pengaruh Kenaikan BBM Terhadap Laju Inflasi di Indonesia”, Jurnal Teknologi dan Manajemen Industri Terapan, 2: 25–32, (2023).
• [6] Satoto, E. B., “The Effect of Fuel Price Fluctuations, Exchange Rates, and Profitability on Stock Returns and Inflation as Intervening Variables”, Jurnal Ilmu Manajemen dan Bisnis, 8: 110-127, (2023).
• [7] Dewi, Y., Saryono, S., Dini, A., Maghfiroh, M., Mauli, R., “Dampak Kenaikan Harga Bahan Bakar Minyak (BBM) Terhadap Sembilan Bahan Pokok (Sembako) Di Kecamatan Tambun Selatan Dalam Masa Pandemi”, Journal Citizenship Virtues, 2: 320–326, (2022).
• [8] Mulyani, S., Novita, R., “Implementation of the Naive Bayes Classifier Algorithm for Classification of Community Sentiment About Depression on Youtube”, Jurnal Teknik Informatika, 3: 1355–1361, (2022).
• [9] Saputra, F. H., Cholifah, C., “Pengaruh Narasi dalam Konten Vlog Channel Youtube ‘Menjadi Manusia’ Terhadap Sikap dalam Menjaga Kesehatan Mental”, Jurnal Ilmu Sosial dan Ilmu Politik, 19: 11–22, (2023).
• [10] Ma’ruf, M., Kuncoro, A. P., Subarkah, P., Nida, F., “Sentiment analysis of customer satisfaction levels on smartphone products using Ensemble Learning”, Ilkom Jurnal Ilmiah, 14(3): 339–347, (2022).
• [11] Nandwani, P., Verma, R., “A review on sentiment analysis and emotion detection from text”, Social Network Analysis and Mining, 11: 81, (2021).
• [12] Mantello, P., Ho, M.-T., Nguyen, M.-H., Vuong, Q.-H., “Bosses without a heart: socio-demographic and cross-cultural determinants of attitude toward Emotional AI in the workplace”, AI and Society, 38: 97–119, (2023).
• [13] Sapanji, R. A. E. V., Targa, T., Hamdani, D., Harahap, P., “Sentiment Analysis of the Top 5 E-commerce Platforms in Indonesia using Text Mining and Natural Language Processing (NLP)”, Journal of Applied Informatics and Computing, 7: 202–211, (2023).
• [14] Sünnetci, K. M., Akben, S. B., Kara, M. M., Alkan, A., “Face mask detection using GoogLeNet CNN-Based SVM Classifiers,” Gazi University Journal of Science, 36: 645–658, (2023).
• [15] Agrawal, S., Dutta, S., Patra, B. K., “Sentiment Analysis of Short Informal Text by Tuning BERT - Bi-LSTM Model”, IEEE EUROCON 2021 - 19th International Conference on Smart Technologies, 98-102, (2021).
• [16] Wibowo, A. P., Darmawan, W., Amalia, N., “Komparasi Metode Naive Bayes dan K-Nearest Neighbor Terhadap Analisis Sentimen Pengguna Aplikasi PeduliLindungi”, IC-Tech Journal, 17: 18–23, (2022).
• [17] Vashishtha, S., Gupta, V., Mittal, M., “Sentiment analysis using fuzzy logic: A comprehensive literature review”, WIREs Data Mining and Knowledge Discovery, 13: 64-101, (2023).
• [18] Tombaloğlu, B., Erdem, H., “Turkish speech recognition techniques and applications of recurrent units (LSTM and GRU)”, Gazi University Journal of Science, 34: 1035–1049, (2021).
• [19] Rahman, A. F., “Klasifikasi Tweet di Twitter dengan Menggunakan Metode K-Nearest Neighbor”, Jurnal Sistim Informatika dan Teknologi, 4: 64–69, (2022).
• [20] Zhang, W., Li, L., Zhu, Y., Yu, P., Wen, J., “CNN-LSTM neural network model for fine-grained negative emotion computing in emergencies”, Alexandria Engineering Journal, 61: 6755–6767, (2022).
• [21] Vimali, J. S., Murugan, S., “A Text Based Sentiment Analysis Model using Bi-directional LSTM Networks”, IEEE ICCES 2021 - 6th International Conference on Communication and Electronics Systems, 1652-1658, (2021).
• [22] Negara, A. B. P., Muhardi, H., Sajid, F., “Perbandingan Algoritma Klasifikasi terhadap Emosi Tweet Berbahasa Indonesia”, Jurnal Edukasi dan Penelititian Informatika, 7: 242-249, (2021).
• [23] Rahman, O. H., Abdillah, G., Komarudin, A., “Klasifikasi Ujaran Kebencian pada Media Sosial Twitter Menggunakan Support Vector Machine”, Jurnal Rekayasa Sistem dan Teknologi Informasi, 5: 17–23, (2021).
• [24] Abri, R., Artuner, H., “LSTM-Based Deep Learning Methods for Prediction of Earthquakes Using Ionospheric Data”, Gazi University Journal of Science, 35: 1417–1431, (2022).
• [25] Tyas, T. M. M., Purnamasari, A. I., “Penerapan Algoritma K-means dalam Mengelompokkan Demam Berdarah Dengue Berdasarkan Kabupaten”, Blend Sains Jurnal Teknik, 1: 277–283, (2023).
• [26] Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., Polosukhin, I., “Attention Is All You Need”, arXiv Preprint, Ithaca, (2023).
• [27] Putra, I. M., Tahyudin, I., Rozaq, H. A. A., A. Syafa’at, Y., Wahyudi, R., Winarto, E., “Classification analysis of COVID19 patient data at government hospital of banyumas using machine learning”, IEEE ICSCEE 2021 - 2nd International Conference on Smart Computing and Electronic Enterprise: Ubiquitous, Adaptive, and Sustainable Computing Solutions for New Normal, 271-274, (2021).
• [28] Tahyudin, I., Rozaq, H. A. A., Nambo, H., “Machine Learning Analysis for Temperature Classification using Bioelectric Potential of Plant”, IEEE ICITISEE 2022 - 6th International Conference on Information Technology, Information Systems and Electrical Engineering, 465-470, (2022).
• [29] Elistiana, K. M., Kusuma, B. A., Subarkah, P., Rozaq, H. A. A., “Improvement of Naive Bayes Algorithm in Sentiment Analysis of Shopee Application Reviews on Google Play Store,” Jurnal Teknik Informatika, 4: 1431–1436, (2023).